Research group

Our research group is part of the METU ImageLab (Follow us on Twitter). We do research in computer vision and machine learning in general. Of special interest are robust recognition, explainable models and medical image analysis. Current members of our research group are as follows (in alphabetical order of first name).

PhD students

Merve Taplı

MSc students

Ahmet Furkan Öztürk

Barış Çağlıyan

Defne Odabaşı

Derya Tınmaz

Co-advisor: Gökberk Cinbiş

Emirhan Bayar

Melih Darcan

Meriç Haliloğlu

Nuray Akar

Sarp Kantar

Tunahan Oğuz

Umut Özdemir

BSc students

Arda Cengiz

Bahar Aşkın

Berna Tanrısever

Co-advisor: Gökberk Cinbiş

Özgür Yıldırım

Co-advisor: Gökberk Cinbiş

Selay Nisa Şahin

Co-advised students

• Can Ufuk Ertenli, PhD student, Advisors: Gökberk Cinbiş, E. Akbas
• Egecan Karadöller, MSc student, Advisors: Bilge Demirköz, E. Akbas
• Gülce Karagöz, PhD student, Advisors: Bilge Demirköz, E. Akbas
• Güneş Çepiç, MSc student, Advisors: Sinan Kalkan, E. Akbas
• Mustafa Uğur Yalçın, MSc student, Advisors: Sinan Kalkan, E. Akbas
• Sezai Artun Özyeğin, PhD student, Advisors: Sinan Kalkan, Kemal Öksüz, E. Akbas
• Şevval Uçar, MSc student, Advisors: Sinan Kalkan, E. Akbas

Past students

• Alper Bahçekapılı, MSc, August 2026.
  Thesis title: “ConWise-FT: Enhancing few-shot learning through contrastive projection tuning and post-training weight ensembling”
• Burak Ferit Aktan, MSc, August 2026. Co-advised with Prof. Sinan Kalkan.
  Thesis title “Long-Tailed Visual Recognition with Learnable Average Precision Loss”
• Bedrettin Çetinkaya, PhD, August 2025. Co-advised with Prof. Sinan Kalkan.
  Thesis title: “Addressing class imbalance, label uncertainty and crispness in edge detection”
• Muhammed Can Keleş, MSc, August 2025. Co-advised with Prof. Sinan Kalkan.
  Thesis title: “Ranking based losses for human pose estimation”
• Erce Güder, MSc, August 2025.
  Thesis title: “Augmenting CLIP-based few-shot recognition using shapes and concepts”
• Devrim Çavuşoğlu, MSc, August 2025.
  Thesis title: “Refurbished embeddings with integrated guidance networks for efficient context-length scaling”
• Onat Özdemir, MSc, August 2025.
  Thesis title: “Interpretable zero-shot classification with concept bottleneck models”
• Şahin Umutcan Üstündaş, MSc, April 2025. Co-advised with Assoc. Prof. Erol Şahin.
  Thesis title: “A novel scalable global alignment method for 3D reconstruction”
• Feyza Yavuz, MSc, Jan 2025. Co-advised with Dr. Kemal Öksüz and Prof. Sinan Kalkan.
  Thesis title: “Bucketing Ranking-based Losses for Efficient Training of Object Detectors”
• Adnan Harun Doğan, MSc, Jan 2025. Co-advised with Dr. Kemal Öksüz and Prof. Sinan Kalkan.
  Thesis title: “Incorporating piecewise linear functions with constant regions in backpropagation”
• Muhammed Yasin Ulaş, MSc, Aug 2024. Co-advised with Prof. Fatos Yarman Vural.
  Thesis title: “Exploiting spatial redundancy in feature maps to accelarate convolution neural networks”
• Sina Şehlaver, MSc, Jul 2024. Co-advised with Prof. Ahmet Acar.
  Thesis title: “The effect of language input in semantic segmentation and grading of colorectal cancer with language-vision models”
• Melih Baydar, PhD, Jul 2024.
  Thesis title: “Self-supervised learning for unsupervised image classification and supervised localization tasks”
• Batuhan Karagöz, PhD, Jul 2024.
  Thesis title: “Exploring dense depth predictions as a supervision source for human pose and shape estimation”
• A. Tarık Temür, MSc, Apr 2024.
  Thesis title: “Real-time joint multi-camera multi-person tracking”
• Çağrı Eser, MSc, Jan 2024. Co-advised with Prof. Sinan Kalkan.
  Thesis title: “Mitigating class imbalance in long-tailed visual recognition through the use of intrinsic dimensionality”
• Ertuğrul Güngör, MSc, Jan 2024. Co-advised with Prof. Sinan Kalkan.
  Thesis title: “On Calibrating Deep Object Detectors”
• İlyas Eren Yılmaz, MSc, Dec 2023. Co-advised with Prof. Erol Şahin.
  Thesis title: “Systematic Evaluation of the Effects of Low-Resolution and Monochrome Images on Instant Neural Graphic Primitives Based 3D Reconstruction”
• Özhan Suat, MSc, Sep 2023.
  Thesis title: “Human pose and shape estimation based on masked mesh modeling from single view RGBD”
• Bedirhan Uğuz, MSc, Jul 2023.
  Thesis title: “Bridging the MoCap-to-Visual domain gap in human mesh recovery from 2D keypoints”
• Raheem K. Hashmani, MSc, Jan 2023. Co-advised with Prof. Bilge Demirköz.
  Thesis title: “A deep learning approach to proton background rejection for positron analysis with the AMS electromagnetic calorimeter”
• Can Ufuk Ertenli, MSc, Sep 2022. Co-advised with Prof. R. Gökberk Cinbiş.
  Thesis title: “Streaming multiscale deep equilibrium models”
• Cansu Cemre Yeşilçimen, MSc, Sep 2022.
  Thesis title: “Image generation using only a discriminator network with gradient norm penalty”
• Fehmi Kahraman, MSc, Aug 2022. Co-advised with Prof. Sinan Kalkan
  Thesis title: “Correlation Loss: Enforcing Correlation Between Classification and Localization in Object Detection”
• Samet Hiçsönmez, PhD, Aug 2022. Main advisor: Prof. Pınar Duygulu Şahin.
  Thesis title: “Generating illustrations for children books using generative adversarial networks”
• Zeynep Sonat Baltacı, MSc, Jul 2022. Co-advised with Dr. Kemal Öksüz and Prof. Sinan Kalkan.
  Thesis title:“Quantifying and mitigating class imbalance in long-tailed visual recognition”
• Gökçen Gökçeoğlu, MSc, Feb 2022.
  Thesis title: “Character Generation Through Self-supervised Vectorization”
• Nermin Samet, PhD, Sep 2021.
  Thesis title: “Integrating near and long-range evidence for visual detection”
• Merve Taplı, MSc, Sep 2021.
  Thesis title: “Image generation by back-propagation on input using a discriminator network”
• Kemal Öksüz, PhD, May 2021. Co-advised with Prof. Sinan Kalkan
  Thesis title: “Identifying and addressing imbalance problems in visual detection”
• Engin Fırat, MSc, Feb 2021.
  Thesis title: “Utilizing video colorization as a self-supervised auxiliary task for object tracking”
• Barış Can Çam, MSc. Sep 2020. Co-advised with Prof. Sinan Kalkan
  Thesis title: “Training Object Detectors by Directly Optimizing LRP Metric”
• Gizem Sarıarslan, MSc. Sep 2019. Co-advised with Prof. Adnan Yazıcı
  Thesis title: “Human Activity Prediction Using Lifelogging Data”
• Bedrettin Çetinkaya, MSc. Aug 2019. Co-advised with Prof. Sinan Kalkan
  Thesis title: “Does Estimated Depth Help Object Detection?”
• Eren Şener, MSc. Aug 2019.
  Thesis title: “Improved Knowledge Distillation with Dynamic Network Pruning”
• Kader Belli, MSc. Jul 2019. Co-advised with Prof. Adnan Yazıcı
  Thesis title: “Activity Prediction from Auto-Captured Lifelog Images”
• Duygu Kabakçı, MSc. Jul 2019.
  Thesis title: “Automated Learning Rate Search Using Micro Level Cross-Validation”
• Ersan Vural Zorlu, MSc. Jul 2019.
  Thesis title: “Rescoring Detections based on Contextual Scores in Object Detection”
• Edanur Demir, MSc. Jan 2019.
  Thesis title: “Early-exit convolutional neural networks”
• Muhammed Kocabaş, MSc. Jan 2019.
  Thesis title: “2D/3D human pose estimation using deep convolutional neural networks”
• Güneş Sucu, MSc. Sep 2017.
  Thesis title: “Decoding cognitive states using the bag of words model on FMRI time series”
• Sadegh Eskandari (Visited our group when he was a PhD student at Shahid Bahonar University of Kerman, Iran – Nov 2016 )

News